1
|
Futterman ID, Sher O, Saroff C, Cohen A, Doulaveris G, Dar P, Griffin MM, Limaye M, Owens T, Brustman L, Rosenberg H, Jessel R, Chudnoff S, Haberman S. Machine Learning for the Prediction of Surgical Morbidity in Placenta Accreta Spectrum. Am J Perinatol 2024. [PMID: 39288819 DOI: 10.1055/a-2405-3459] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 09/19/2024]
Abstract
OBJECTIVE We sought to create a machine learning (ML) model to identify variables that would aid in the prediction of surgical morbidity in cases of placenta accreta spectrum (PAS). STUDY DESIGN A multicenter analysis including all cases of PAS identified by pathology specimen confirmation, across five tertiary care perinatal centers in New York City from 2013 to 2022. We developed models to predict operative morbidity using 213 variables including demographics, obstetrical information, and limited prenatal imaging findings detailing placental location. Our primary outcome was prediction of a surgical morbidity composite defined as including any of the following: blood loss (>1,500 mL), transfusion, intensive care unit admission, vasopressor use, mechanical ventilation/intubation, and organ injury. A nested, stratified, cross-validation approach was used to tune model hyperparameters and estimate generalizability. Gradient boosted tree classifier models incorporated preprocessing steps of standard scaling for numerical variables and one-hot encoding for categorical variables. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), positive and negative predictive values (PPV, NPV), and F1 score. Variable importance ranking was also determined. RESULTS Among 401 PAS cases, 326 (81%) underwent hysterectomy. Of the 401 cases of PAS, 309 (77%) had at least one event defined as surgical morbidity. Our predictive model had an AUC of 0.79 (95% confidence interval: 0.69, 0.89), PPV 0.79, NPV 0.76, and F1 score of 0.88. The variables most predictive of surgical morbidity were completion of a hysterectomy, prepregnancy body mass index (BMI), absence of a second trimester ultrasound, socioeconomic status zip code, BMI at delivery, number of prenatal visits, and delivery time of day. CONCLUSION By identifying social and obstetrical characteristics that increase patients' risk, ML models are useful in predicting PAS-related surgical morbidity. Utilizing ML could serve as a foundation for risk and complexity stratification in cases of PAS to optimize surgical planning. KEY POINTS · ML models are useful models are useful in predicting PAS-related surgical morbidity.. · Optimal management for PAS remains unclear.. · Utilizing ML can serve as a foundation for risk and complexity stratification in cases of PAS..
Collapse
Affiliation(s)
- Itamar D Futterman
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Maimonides Medical Center, Brooklyn, New York
- Division of Complex Obstetrical Surgery, Department of Obstetrics and Gynecology, Maimonides Medical Center, Brooklyn, New York
| | - Olivia Sher
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Maimonides Medical Center, Brooklyn, New York
| | | | - Alexa Cohen
- Division of Fetal Medicine and Ultrasound, Obstetrics, Gynecology and Women's Health, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, New York
| | - Georgios Doulaveris
- Division of Fetal Medicine and Ultrasound, Obstetrics, Gynecology and Women's Health, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, New York
| | - Pe'er Dar
- Division of Fetal Medicine and Ultrasound, Obstetrics, Gynecology and Women's Health, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, New York
| | - Myah M Griffin
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, NYU Langone Medical Center, New York, New York
| | - Meghana Limaye
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, NYU Langone Medical Center, New York, New York
| | - Thomas Owens
- Division of Maternal Fetal Medicine, Mount Sinai West, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Lois Brustman
- Division of Maternal Fetal Medicine, Mount Sinai West, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Henri Rosenberg
- Division of Maternal Fetal Medicine, Department of Obstetrics, Gynecology and Reproductive Science, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Rebecca Jessel
- Division of Maternal Fetal Medicine, Department of Obstetrics, Gynecology and Reproductive Science, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Scott Chudnoff
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Maimonides Medical Center, Brooklyn, New York
| | - Shoshana Haberman
- Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Maimonides Medical Center, Brooklyn, New York
| |
Collapse
|
2
|
Brown JA, Huff ML, Arboleda BL, Louis JM. The Relationship between Body Mass Index and Operative Complications in Patients undergoing Immediate Postpartum Tubal Ligation. Am J Perinatol 2024; 41:909-914. [PMID: 35253112 DOI: 10.1055/a-1788-4900] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/01/2022]
Abstract
OBJECTIVE The objective of this study is to examine the relationship between body mass index (BMI) and complications for patients undergoing postpartum permanent contraception. STUDY DESIGN Retrospective cohort study of patients aged 18 or older who had a vaginal delivery at an academic hospital between 2011 and 2016 and underwent a postpartum tubal ligation during the delivery admission. There were three comparative groups: nonobese (BMI ≤ 29 kg/m2), obese (BMI 30-39 kg/m2), and morbidly obese BMI (≥40 kg/m2). The outcome of interest was composite operative complications which included any occurrence of an intraoperative, postoperative, or anesthesia complication. RESULTS A total of 921 patients were included for analysis. Average operative time was statistically longer for patients in the morbidly obese group (33 minutes) vs. the nonobese (25 minutes) and obese (29 minutes) groups (p < 0.0001). Composite complications were greater for the obese groups, but not statistically significant (5.1 vs. 6 vs. 16%, p = 0.06). Wound complications were significantly greater for the obese groups (0.8 vs. 1.5 vs. 5.5%, p = 0.01). A logistic regression model demonstrated that only operative time was predictive of operative complications. CONCLUSION Overall complications of postpartum tubal complications are low; however, our study did demonstrate significantly longer operative time and wound complications for patients with obesity. The findings of our study indicate that postpartum permanent contraception can remain as an option for these patients. Further studies may help identify the best practices to decrease operative time and subsequent wound complications. This study contributes to the limited data regarding obesity and postpartum permanent contraception. We found increased operative time and wound complications for obese patients. Additional studies may identity best practices to decrease these complications. Given our findings of overall low operative complications, postpartum permanent contraception can remain an option for obese patients.
Collapse
Affiliation(s)
- Jewel A Brown
- Department of Obstetrics and Gynecology, University of South Florida Morsani College of Medicine, Tampa, Florida
- Tampa General Circle, STC, Tampa, Florida
- Department of Obstetrics and Gynecology, University of California Davis Health, Sacramento, California
| | - Mallorie L Huff
- Department of Obstetrics and Gynecology, University of South Florida Morsani College of Medicine, Tampa, Florida
| | - Bianca L Arboleda
- Department of Obstetrics and Gynecology, University of South Florida Morsani College of Medicine, Tampa, Florida
- Department of Obstetrics and Gynecology, University of Kentucky, Lexington, Kentucky
| | - Judette M Louis
- Department of Obstetrics and Gynecology, University of South Florida Morsani College of Medicine, Tampa, Florida
| |
Collapse
|
3
|
Aedla NR, Mahmood T, Ahmed B, Konje JC. Challenges in timing and mode of delivery in morbidly obese women. Best Pract Res Clin Obstet Gynaecol 2024; 92:102425. [PMID: 38150814 DOI: 10.1016/j.bpobgyn.2023.102425] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 10/31/2023] [Accepted: 11/13/2023] [Indexed: 12/29/2023]
Abstract
Globally obesity is increasing especially in the reproductive age group. Pregnant women with obesity have higher complication and intervention rates. They are also at increased risk of stillbirth and intrapartum complications. Although organisations like NICE, RCOG, ACOG and WHO have published guidelines and recommendations on care of pregnant women with obesity the evidence from which Grade A recommendations can be made on timing and how to deliver is limited. The current advice is therefore to have discussions with the woman on risks to help her make an informed decision about timing, place, and mode of delivery. Obesity is an independent risk factor for pregnancy complications including diabetes, hypertension and macrosomia. In those with these complications, the timing of delivery is often influenced by the severity of the complication. As an independent factor, population based observational studies in obese women have shown an increase in the risk of stillbirth. This risk increases linearly with weight from overweight through to class II obesity, but then rises sharply in those with class III obesity by at least 10-fold beyond 42 weeks when compared to normal weight women. This risk of stillbirth is notably higher in obese women from 34 weeks onwards compared to normal weight women. One modifiable risk factor for stillbirth as shown from various cohorts of pregnant women is prolonged pregnancy. Research has linked obesity to prolonged pregnancy. Although the exact mechanism is yet unknown some have linked this to maternal dysregulation of the hypothalamic pituitary adrenal axis leading to hormonal imbalance delaying parturition. For these women the two dilemmas are when and how best to deliver. In this review, we examine the evidence and make recommendations on the timing and mode of delivery in women with obesity. For class I obese women there are no differences in outcome with regards to timing and mode of delivery when compared to lean weight women. However, for class II and III obesity, planned induction or caesarean sections may be associated with a lower perinatal morbidity and mortality although this may be associated with an increased in maternal morbidity especially in class III obesity. Studies have shown that delivery by 39 weeks is associated with lower perinatal mortality compared to delivering after in these women. On balance the evidence would favour planned delivery (induction or caesarean section) before 40 weeks of gestation. In the morbidly obese, apart from the standard lower transverse skin incision for CS, there is evidence that a supraumbilical transverse incision may reduce morbidity but is less cosmetic. Irrespective of the option adopted, it is important to discuss the pros and cons of each.
Collapse
Affiliation(s)
- Nivedita R Aedla
- Simpsons Centre for Reproductive Medicine Royal Infirmary of Edinburgh, Edinburgh, UK.
| | | | - Badreldeen Ahmed
- Fetal Maternal Centre, Doha, Qatar; Weill Cornell Medicine Qatar. Qatar; University of Qatar, Qatar
| | - Justin C Konje
- Fetal Maternal Centre, Doha, Qatar; Weill Cornell Medicine Qatar. Qatar; Department of Health Sciences, University of Leicester, UK; University of Ho, Ghana
| |
Collapse
|
4
|
Gillespie BM, Webster J, Ellwood D, Thalib L, Whitty JA, Mahomed K, Clifton V, Kumar S, Wagner A, Kang E, Chaboyer W. Closed incision negative pressure wound therapy versus standard dressings in obese women undergoing caesarean section: multicentre parallel group randomised controlled trial. BMJ 2021; 373:n893. [PMID: 33952438 PMCID: PMC8097312 DOI: 10.1136/bmj.n893] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
OBJECTIVE To determine the effectiveness of closed incision negative pressure wound therapy (NPWT) compared with standard dressings in preventing surgical site infection (SSI) in obese women undergoing caesarean section. DESIGN Multicentre, pragmatic, randomised, controlled, parallel group, superiority trial. SETTING Four Australian tertiary hospitals between October 2015 and November 2019. PARTICIPANTS Eligible women had a pre-pregnancy body mass index of 30 or greater and gave birth by elective or semi-urgent caesarean section. INTERVENTION 2035 consenting women were randomised before the caesarean procedure to closed incision NPWT (n=1017) or standard dressing (n=1018). Allocation was concealed until skin closure. MAIN OUTCOME MEASURES The primary outcome was cumulative incidence of SSI. Secondary outcomes included depth of SSI (superficial, deep, or organ/body space), rates of wound complications (dehiscence, haematoma, seroma, bleeding, bruising), length of stay in hospital, and rates of dressing related adverse events. Women and clinicians were not masked, but the outcome assessors and statistician were blinded to treatment allocation. The pre-specified primary intention to treat analysis was based on a conservative assumption of no SSI for a minority of women (n=28) with missing outcome data. Post hoc sensitivity analyses included best case analysis and complete case analysis. RESULTS In the primary intention to treat analysis, SSI occurred in 75 (7.4%) women treated with closed incision NPWT and in 99 (9.7%) women with a standard dressing (risk ratio 0.76, 95% confidence interval 0.57 to 1.01; P=0.06). Post hoc sensitivity analyses to explore the effect of missing data found the same direction of effect (closed incision NPWT reducing SSI), with statistical significance. Blistering occurred in 40/996 (4.0%) women who received closed incision NPWT and in 23/983 (2.3%) who received the standard dressing (risk ratio 1.72, 1.04 to 2.85; P=0.03). CONCLUSION Prophylactic closed incision NPWT for obese women after caesarean section resulted in a 24% reduction in the risk of SSI (3% reduction in absolute risk) compared with standard dressings. This difference was close to statistical significance, but it likely underestimates the effectiveness of closed incision NPWT in this population. The results of the conservative primary analysis, multivariable adjusted model, and post hoc sensitivity analysis need to be considered alongside the growing body of evidence of the benefit of closed incision NPWT and given the number of obese women undergoing caesarean section globally. The decision to use closed incision NPWT must also be weighed against the increases in skin blistering and economic considerations and should be based on shared decision making with patients. TRIAL REGISTRATION ANZCTR identifier 12615000286549.
Collapse
Affiliation(s)
- Brigid M Gillespie
- National Health and Medical Research Council Centre of Research Excellence in Wiser Wound Care, Menzies Health Institute, Griffith University, Gold Coast, Qld, Australia
- Gold Coast University Hospital, Gold Coast Health, Southport, Qld, Australia
| | - Joan Webster
- Centre for Clinical Nursing, Royal Brisbane and Women's Hospital, Herston, Qld, Australia
| | - David Ellwood
- Gold Coast University Hospital, Gold Coast Health, Southport, Qld, Australia
- School of Medicine and Dentistry, Griffith University, Gold Coast, Qld, Australia
| | - Lukman Thalib
- School of Nursing and Midwifery, Griffith University, Gold Coast, Qld, Australia
| | - Jennifer A Whitty
- Norwich Medical School, University of East Anglia, Norwich, UK
- National Institute for Health Research Applied Research Collaboration (ARC) East of England (EoE), Norwich, UK
| | - Kassam Mahomed
- Ipswich Hospital, West Moreton Health, Ipswich, Qld, Australia
| | - Vicki Clifton
- Mater Research Institute, University of Queensland, South Brisbane, Qld, Australia
| | - Sailesh Kumar
- Mater Research Institute, University of Queensland, South Brisbane, Qld, Australia
- Mater Mothers' Hospital, South Brisbane, Qld, Australia
| | - Adam Wagner
- Norwich Medical School, University of East Anglia, Norwich, UK
- National Institute for Health Research Applied Research Collaboration (ARC) East of England (EoE), Norwich, UK
| | - Evelyn Kang
- National Health and Medical Research Council Centre of Research Excellence in Wiser Wound Care, Menzies Health Institute, Griffith University, Gold Coast, Qld, Australia
| | - Wendy Chaboyer
- National Health and Medical Research Council Centre of Research Excellence in Wiser Wound Care, Menzies Health Institute, Griffith University, Gold Coast, Qld, Australia
| |
Collapse
|
5
|
A Systematic Review and Meta-Analysis of Wound Complications after a Caesarean Section in Obese Women. J Clin Med 2021; 10:jcm10040675. [PMID: 33578671 PMCID: PMC7916387 DOI: 10.3390/jcm10040675] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2020] [Revised: 02/01/2021] [Accepted: 02/07/2021] [Indexed: 12/16/2022] Open
Abstract
(1) Background: Caesarean sections in obese patients are associated with an increased risk of surgical wound complications, including hematomas, seromas, abscesses, dehiscence, and surgical site infections. The aim of the present study is to perform a meta-analysis and systematic review of the current literature focusing on the strategies available to decrease wound complications in this population. (2) Methods: We reviewed the data available from the PubMed and the Science Direct databases concerning wound complications after caesarean sections in obese women. The following key words were used: “caesarean section”, “cesarean section”, “wound complication”, “wound morbidity”, and “wound infection”. A total of 540 papers were retrieved, 40 of which were selected for the final systematic review and whereas 21 articles provided data for meta-analysis. (3) Results: The conducted meta-analyses revealed that the use of prophylactic drainage does not increase the risk of wound complications in obese women after a caesarean sections (pooled OR = 1.32; 95% CI 0.64–2.70, p = 0.45) and that vertical skin incisions increase wound complications (pooled OR = 2.48; 95% CI 1.85–3.32, p < 0.01) in obese women, including extremely obese women. (4) Conclusions: Subcutaneous drainage does not reduce the risk of a wound complications, wound infections, and fever in obese women after caesarean sections. Negative prophylactic pressure wound therapy (NPWT) may reduce the risk of surgical site infections. The evidence of using a prophylactic dose of an antibiotic before the caesarean section is still lacking.
Collapse
|
6
|
Maternal morbidity associated with skin incision type at cesarean delivery in obese patients: a systematic review. Future Sci OA 2020; 7:FSO669. [PMID: 33552545 PMCID: PMC7850001 DOI: 10.2144/fsoa-2020-0160] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/02/2022] Open
Abstract
Aim: To describe the relationship between cesarean skin incision type and postoperative wound complications (WCs) in obese pregnant patients. Materials & methods: MEDLINE (PubMed and OVID), Embase, Scopus, Web of Science Core Collection, Cochrane Library and ClinicalTrials.gov databases were used for publication search. Selection criteria consisted of articles studying pregnant patients with BMI ≥30 kg/m2 undergoing cesarean delivery and assessing the effect of skin incision type on postoperative maternal outcomes. Results: Ten publications met criteria for a systematic review of a total of 2946 patients. The transverse skin incision was associated with a lower rate of WC compared with the vertical skin incision. The pooled risk ratio for WCs was 0.47 (95% CI: 0.37–0.58; p < 0.00001). Conclusion: Transverse skin incision may be preferable to vertical skin incision at cesarean delivery in pregnant patients with obesity as it may be associated with a lower rate of WCs. PROSPERO registration ID: CRD42020151106 This systematic review describes the relationship between skin incision type and postoperative wound complications in obese patients following cesarean delivery. The study results suggest that transverse skin incisions may be preferable to vertical skin incisions in the obese obstetric population for the reduction of wound complications.
Collapse
|